2 papers
cs.LG2026
Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design
Sanna Jarl, Maria Bånkestad, Jonathan J. S. Scragg +1
In many experimental settings, active learning can improve sample efficiency by sequentially selecting where to measure, which is particularly valuable when experiments are expensi…
cs.LG2025
Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
Sanna Jarl, Jens Sjölund, Robert J. W. Frost +2
Self-driving labs (SDLs), employing automation and machine learning (ML) to accelerate experimental procedures, have enormous potential in the discovery of new materials. However,…